Systems and methods for automated identification of emerging trends

Abstract

Systems and methods for automated identification of emerging trends are disclosed. A method may include: (1) receiving, by a computer program executed on an electronic device, a plurality of documents; (2) training, by the computer program, a proximity model to identify word pairs in each of the plurality of documents, wherein the word pairs comprise two words within a predetermined distance of each other at a predetermined frequency in the plurality of documents; (3) identifying, by the computer program and using the proximity model, trends involving the word pairs, wherein the trends are based on a frequency that the word pairs appear in the plurality of documents and/or a velocity at which the word pairs appear in the plurality of documents over a period of time; and (4) outputting, by the computer program, the word pairs and the trends to a downstream system.

What is claimed is: 
     
         1 . A method for automated identification of emerging trends, comprising:
 receiving, by a computer program executed on an electronic device, a plurality of documents;   training, by the computer program, a proximity model to identify word pairs in each of the plurality of documents, wherein the word pairs comprise two words within a predetermined distance of each other at a predetermined frequency in the plurality of documents;   identifying, by the computer program and using the proximity model, trends involving the word pairs, wherein the trends are based on a frequency that the word pairs appear in the plurality of documents and/or a velocity at which the word pairs appear in the plurality of documents over a period of time; and   outputting, by the computer program, the word pairs and the trends to a downstream system.   
     
     
         2 . The method of  claim 1 , wherein the plurality of documents comprise publications, web pages, articles, and/or news streams. 
     
     
         3 . The method of  claim 1 , wherein the plurality of documents comprise call logs and/or chat logs. 
     
     
         4 . The method of  claim 1 , wherein the plurality of documents comprise text that was converted from audio. 
     
     
         5 . The method of  claim 1 , wherein the word pairs are identified with a predetermined range of each other. 
     
     
         6 . The method of  claim 1 , wherein each of the word pairs comprise an anchor word and a second word that is within the predetermined distance of the anchor word. 
     
     
         7 . The method of  claim 1 , further comprising:
 identifying, by the computer program, a word that is a result of one of the word pairs merging.   
     
     
         8 . A system, comprising:
 a source of a plurality of documents;   a pivot word database comprising a plurality of pivot words;   a word pair database;   a downstream system; and   an electronic device executing a computer program that is configured to receive the plurality of documents from the source, train a proximity model to identify word pairs in each of the plurality of documents, wherein the word pairs comprise two words within a predetermined distance of each other at a predetermined frequency in the plurality of documents, store the word pairs in the word pair database, identify, using the proximity model, trends involving the word pairs, wherein the trends are based on a frequency that the word pairs appear in the plurality of documents and/or a velocity at which the word pairs appear in the plurality of documents over a period of time, and output the word pairs and the trends to the downstream system.   
     
     
         9 . The system of  claim 8 , wherein the plurality of documents comprise publications, web pages, articles, and/or news streams. 
     
     
         10 . The system of  claim 8 , wherein the plurality of documents comprise call logs and/or chat logs. 
     
     
         11 . The system of  claim 8 , wherein the plurality of documents comprise text that was converted from audio. 
     
     
         12 . The system of  claim 8 , wherein the word pairs are identified with a predetermined range of each other. 
     
     
         13 . The system of  claim 8 , wherein each of the word pairs comprise an anchor word and a second word that is within the predetermined distance of the anchor word. 
     
     
         14 . The system of  claim 8 , wherein the computer program is further configured to identify a word that is a result of one of the word pairs merging. 
     
     
         15 . A non-transitory computer readable storage medium, including instructions stored thereon, which when read and executed by one or more computer processors, cause the one or more computer processors to perform steps comprising:
 receiving a plurality of documents;   training a proximity model to identify word pairs in each of the plurality of documents, wherein the word pairs comprise two words within a predetermined distance of each other at a predetermined frequency in the plurality of documents;   identifying, using the proximity model, trends involving the word pairs, wherein the trends are based on a frequency that the word pairs appear in the plurality of documents and/or a velocity at which the word pairs appear in the plurality of documents over a period of time; and   outputting the word pairs and the trends to a downstream system.   
     
     
         16 . The non-transitory computer readable storage medium of  claim 15 , wherein the plurality of documents comprise publications, web pages, articles, news streams, call logs and/or chat logs. 
     
     
         17 . The non-transitory computer readable storage medium of  claim 15 , wherein the plurality of documents comprise text that was converted from audio. 
     
     
         18 . The non-transitory computer readable storage medium of  claim 15 , wherein the word pairs are identified with a predetermined range of each other. 
     
     
         19 . The non-transitory computer readable storage medium of  claim 15 , wherein each of the word pairs comprise an anchor word and a second word that is within the predetermined distance of the anchor word. 
     
     
         20 . The non-transitory computer readable storage medium of  claim 15 , further including instructions stored thereon, which when read and executed by one or more computer processors, cause the one or more computer processors to perform steps comprising:
 identifying a word that is a result of one of the word pairs merging.